Workload balancing and throughput optimization for heterogeneous systems subject to failures

Authors:
Anne Benoit;Alexandru Dobrila;Jean-Marc Nicod;Laurent Philippe
Affiliations:
ENS Lyon, Université de Lyon, LIP laboratory (ENS, CNRS, INRIA, UCBL), France;niversité de Franche-Comté, LIFC laboratory, France;niversité de Franche-Comté, LIFC laboratory, France;Université de Franche-Comté, LIFC laboratory, France
Venue:
Euro-Par'11 Proceedings of the 17th international conference on Parallel processing - Volume Part I
Year:
2011

Citing 9
Cited 0

Scheduling Multiprocessor Tasks to Minimize Schedule Length

IEEE Transactions on Computers
Fault tolerance in distributed systems

Fault tolerance in distributed systems
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness
Coupling Dynamic Load Balancing with Asynchronism in Iterative Algorithms on the Computational Grid

IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Efficient task replication and management for adaptive fault tolerance in mobile Grid environments

Future Generation Computer Systems - Special section: Information engineering and enterprise architecture in distributed computing environments
On the efficacy, efficiency and emergent behavior of task replication in large distributed systems

Parallel Computing
Towards a general model of the multi-criteria workflow scheduling on the grid

Future Generation Computer Systems
Dynamic Window-Constrained Scheduling for Multimedia Applications

ICMCS '99 Proceedings of the 1999 IEEE International Conference on Multimedia Computing and Systems - Volume 02
Analysis of a window-constrained scheduler for real-time and best-effort packet streams

RTSS'10 Proceedings of the 21st IEEE conference on Real-time systems symposium

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we study the problem of optimizing the throughput of streaming applications for heterogeneous platforms subject to failures. The applications are linear graphs of tasks (pipelines), and a type is associated to each task. The challenge is to map tasks onto the machines of a target platform, but machines must be specialized to process only one task type, in order to avoid costly context or setup changes. The objective is to maximize the throughput, i.e., the rate at which jobs can be processed when accounting for failures. For identical machines, we prove that an optimal solution can be computed in polynomial time. However, the problem becomes NP-hard when two machines can compute the same task type at different speeds. Several polynomial time heuristics are designed, and simulation results demonstrate their efficiency.